The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape
ACM Computing Surveys · 30.09.2025 · 57 (9) · 1-37
DOI: 10.1145/3724113 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 03.04.2025. Verfasst von Joshua Zhao und 9 weiteren Autor:innen. Die Arbeit wurde bisher 70-mal zitiert (Crossref) und nennt 151 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Cisco Research, the DEVCOM ARL Army Research Office, National Science Foundation, Cisco Research and the National Science Foundation.
Abstract (Originalsprache)
Deep learning has shown incredible potential across a wide array of tasks, and accompanied by this growth has been an insatiable appetite for data. However, a large amount of data needed for enabling deep learning is stored on personal devices, and recent concerns on privacy have further highlighted challenges for accessing such data. As a result, federated learning (FL) has emerged as an important privacy-preserving technology that enables collaborative training of machine learning models without the need to send the raw, potentially sensitive, data to a central server. However, the fundamental premise that sending model updates to a server is privacy-preserving only holds if the updates cannot be “reverse engineered” to infer information about the private training data. It has been shown under a wide variety of settings that this privacy premise does not hold. In this article we provide a comprehensive literature review of the different privacy attacks and defense methods in FL. We identify the current limitations of these attacks and highlight the settings in which the privacy of an FL client can be broken. We further dissect some of the successful industry applications of FL and draw lessons for future successful adoption. We survey the emerging landscape of privacy regulation for FL and conclude with future directions for taking FL toward the cherished goal of generating accurate models while preserving the privacy of the data from its participants.
Förderung
- Cisco Research, the DEVCOM ARL Army Research Office
- National Science Foundation
- Cisco Research and the National Science Foundation
- DEVCOM ARL Army Research Office
- NSF
Zitieren
APA
Zhao, J., Bagchi, S., Avestimehr, S., Chan, K., Chaterji, S., Dimitriadis, D., Li, J., Li, N., Nourian, A., & Roth, H. (2025). The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape. ACM Computing Surveys, 57(9), 1-37. https://doi.org/10.1145/3724113
Vancouver
Zhao J, Bagchi S, Avestimehr S, Chan K, Chaterji S, Dimitriadis D, et al. The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape. ACM Computing Surveys. 2025;57(9):1-37. doi:10.1145/3724113
BibTeX
@article{Zhao2025,
author = {Zhao, Joshua and Bagchi, Saurabh and Avestimehr, Salman and Chan, Kevin and Chaterji, Somali and Dimitriadis, Dimitris and Li, Jiacheng and Li, Ninghui and Nourian, Arash and Roth, Holger},
title = {The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape},
journal = {ACM Computing Surveys},
year = {2025},
volume = {57},
number = {9},
pages = {1--37},
doi = {10.1145/3724113}
}
EUVIMED